The lockdown effect: Implications of the COVID-19 pandemic on internet traffic

Coordinators: Franziska Lichtblau, Oliver Gasser

In January 2020 the COVID-19 pandemic, a coronavirus variant spreading across the entire globe, reached central Europe. In the beginning, many people underestimated the impact the virus would have on our entire life in the coming months. Once the first lockdown was imposed in March it quickly became clear that things would drastically change. The Internet was a vital component to maintain as much normality as possible: Many people started to
work from home, with shops partially closed online shopping became even more relevant, artists made first attempts to stream concerts, video streaming at home quickly became one of the few possible leisure activities, and schools relied on remote teaching. With this increased demand the question arose whether the Internet can serve that demand or if it was near a collapse. To investigate this issue we started the COVID measurement project.

As of May 2020, this project consists of a conference paper at the Internet Measurement Conference (ACM IMC) 2020 [1] and several talks reflecting on the results. The fundamental question of this project is if increased Internet traffic demands of residential users, in particular, for remote working, entertainment, commerce, and education due to the lockdown caused traffic shifts in the Internet core. We rely on a diverse set of vantage points, namely one Internet Service Provider (ISP), three Internet Exchange Point (IXP), and one metropolitan educational network, to shed light on the questions from as many angles as possible. The ISP provides us with a view on residential customers and small enterprises; the IXP facilitates interconnection between different businesses; and the educational network allows us to study the changes on a university campus. We find that the traffic volume increased by 15-20% almost within a week — while overall still modest, this constitutes a large increase within this short time period. However, despite this surge, we observe that the Internet infrastructure can handle the new volume, as most traffic shifts occur outside of traditional peak hours.

When looking directly at the traffic sources, it turns out that, while hypergiants (a group of networks responsible for a large fraction of Internet traffic) still contribute a significant fraction of traffic, we see (1) a higher increase in traffic of non-hypergiants, and (2) traffic increases in applications that people use when at home, such as Web conferencing, VPN, and gaming. While many networks see increased traffic demands, in particular, those providing services to residential users, academic networks experience major overall decreases. Yet, in these networks, we can observe substantial increases when considering applications associated with remote working and lecturing. Overall, we indeed find shifts in the traffic usage patterns, especially for residential customers. Nevertheless, from our perspective the Internet did cope quite well with the increased demand. At our vantage points quick reaction times, well-organized structures, and flexible capacity planning allowed them to accommodate the quick change and new customer needs.

References
[1] A. Feldmann, O. Gasser, F. Lichtblau, E. Pujol, I. Poese, C. Dietzel, D. Wagner, M. Wichtlhuber, J. Tapiador, N. Vallina-Rodriguez, O. Hohlfeld, and G. Smaragdakis. The lockdown effect: Implications of the COVID-19 pandemic on internet traffic. In IMC’20, 20th ACM Internet Measurement Conference, Virtual Event, USA, 2020, pp. 1–18. ACM.